Computerized EEG pattern classification by adaptive segmentation and probability-density-function classification. Description of the method.

A phenomenological model for the representation of clinical EEGs is proposed. It assumes each individual record to consist of a few repetitive patterns which are described sufficiently by their power spectra. An algorithm for automatic EEG evaluation is described. It consists of two steps, a segmentation process which isolates the elementary patterns, and a clustering procedure which groups similar patterns with each other. Results are represented in graphical form. Diagnostic classification is not attempted. An appendix highlights the advantages of autoregressive modelling for EEG spectral analysis and, in particular, the estimation of the power contained in the various "rhythms".